R语言 tidyverse系列学习笔记（系列2）表格的处理

创建一个得分表 score

install.packages("dplyr")
library(dplyr)

install.packages("tibble")
library(tibble)

install.packages("stringr")
library(stringr)

score = tibble(ID=c("1222-1","2001-0","3321-1","4898-0","2782-0","1002-8","4211-0","1023-1","3325-1"),
          gender=c("female","male","male","male","female","female","male","female","male") ,
          chinese_mid_score=round(runif(9,80,90),digits = 0),
          chinese_final_score=round(runif(9,80,90),digits = 0),
          english_score=c(round(runif(8,80,90),digits = 0),NA),
          match_score=round(runif(9,80,90),digits = 0),
          musci_score=round(runif(9,80,90),digits = 0)
               )

view(score)

其中

round(runif(9,80,90),digits = 0)

这段代码是在 R 语言中生成一个长度为 9 的随机数向量，向量中的每个元素都是在 80 到 90 之间的均匀分布的随机数，并使用 round 函数将这些随机数四舍五入为整数。其中，runif 函数用于生成均匀分布的随机数，digits 参数指定保留的小数位数，而 round 函数用于将随机数四舍五入为整数。因此，这段代码生成的向量中的每个元素都是 80 到 90 之间的整数。

c(round(runif(8,80,90),digits = 0),NA)

设置最后一个数据为缺失值，用 NA 表示

对 列 进行处理

contains

···当列数很多时，select 逐个输入想要的列太浪费时间，用contains筛选包含某关键词的列

score_column1 = score |> 
  select(contains("chinese")|contains("english"))

names(score_column1)

除了contains，还可以用 matches

matches

score_column4 = score |> 
  select(matches("mid|final"))

names(score_column4)

starts_with , ends_with

筛选以某字符串 开头starts_with 或 结尾ends_with 的列

score_column2 = score |> 
  select(starts_with("chinese"))

names(score_column2)


score_column3 = score |> 
  select(ends_with("score"))

names(score_column3)

对 行 进行处理

根据 ID 修改

str_detect(score$ID,"-1")

score_pattern = score |> 
  subset(str_detect(ID,"-1") == TRUE)
view(score_pattern)

strsplit("1222-0","-")
strsplit("1222-0","-")[[1]][1]
strsplit("1222-0","-")[[1]][2]

rowwise

score_subID = score |>
  mutate(SubID = strsplit(ID,"-")[[1]][1])
view(score_subID)

在mutate之前加上rowrise可以逐行处理

score_subID = score |>
  rowwise() |> 
  mutate(SubID = strsplit(ID,"-")[[1]][1])
view(score_subID)

case_when

score_case_when = score |>
  rowwise() |> 
  mutate(subID1 = strsplit(ID,"-")[[1]][1]) |> 
  mutate(subID2 = strsplit(ID,"-")[[1]][2]) |> 
  mutate(grade = case_when(
    subID1>=4000 ~"forth",
    subID1>=3000 ~"third",
    subID1>=2000 ~"second",
    subID1>=1000 ~"first"
  ))


view(score_case_when)

case_when最难满足的条件放在最前边，最容易满足的条件放在最后
这样计算出来的结果才精准

对 行 求和

rowwise()很重要，不加的话会出现计算问题

score_rank = score |> 
  rowwise() |> 
  mutate(total_score=sum(chinese_mid_score,chinese_final_score,english_score,match_score,musci_score,na.rm=TRUE))
view(score_rank)

按性别，分数由高到低排序

score_rank = score |> 
  rowwise() |> 
  mutate(total_score=sum(chinese_mid_score,chinese_final_score,english_score,match_score,musci_score,na.rm=TRUE)) |> 
  arrange(gender,desc(total_score))
  
view(score_rank)

只保留男生女生的最高分，可以用distinct，也可以用slice_max

score_rank = score |> 
  rowwise() |> 
  mutate(total_score=sum(chinese_mid_score,chinese_final_score,english_score,match_score,musci_score,na.rm=TRUE)) |> 
  arrange(gender,desc(total_score)) |> 
  distinct(gender,.keep_all = TRUE)

view(score_rank)

score_rank = score |> 
  rowwise() |> 
  mutate(total_score=sum(chinese_mid_score,chinese_final_score,english_score,match_score,musci_score,na.rm=TRUE)) |> 
  group_by(gender) |> 
  slice_max(total_score, n=2)

view(score_rank)

slice_max 的 n=2 时

slice_max 有 n 这个参数，可以更灵活控制输出